CtrlK
BlogDocsLog inGet started
Tessl Logo

review-change

Review a Go change when the user asks to inspect a diff for correctness.

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./examples/complete/skills/review-change/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is admirably concise and the two-step workflow is clearly sequenced, but the guidance is abstract rather than executable and the existing reference file (review-guide.md) is orphaned from the body. Adding concrete inspection/reporting methods and linking the guide would lift the weakest dimensions.

Suggestions

Add concrete, executable guidance for Step 1 (e.g., specific commands or methods to view the diff and surrounding code) so the skill is actionable rather than abstract.

Reference references/review-guide.md from the body (e.g., "Prioritize per references/review-guide.md") so the existing bundle file is discoverable and navigable.

Specify how findings should be reported in Step 2 (e.g., format, required fields like file:line, severity) to move from high-level hints to concrete instructions.

DimensionReasoningScore

Conciseness

The body is extremely lean ("Inspect the complete diff and the surrounding code", "Report correctness, security, and test-coverage findings with file locations") with no padding or explanation of concepts Claude already knows, matching the lean-and-efficient anchor.

5 / 5

Actionability

Guidance is high-level ("Inspect the complete diff and the surrounding code", "Report ... findings with file locations") without specifying how to inspect the diff, what tools or commands to run, or how to structure findings, fitting the minimal-concrete-guidance anchor.

2 / 5

Workflow Clarity

A clear two-step sequence (read the change, then report findings) with explicit ordering ("Process steps in order. Do not skip ahead.") and boundaries ("Proceed immediately to Step 2", "Finish here"); this is a read-only review so the missing validation checkpoint is a minor gap rather than a disqualifier.

4 / 5

Progressive Disclosure

The body is well-sectioned but the provided bundle file references/review-guide.md is never linked or signaled from the body, so the reference is present but not clearly navigable, fitting the some-structure / references-not-clearly-signaled anchor.

3 / 5

Total

14

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly answers both what the skill does and when to use it, with a concrete Go/diff trigger phrase. Its main weakness is limited breadth of trigger synonyms and a single action, which keeps it just below the top anchors.

DimensionReasoningScore

Specificity

"Review a Go change" names the domain (Go diffs) and one concrete action (review for correctness), matching the anchor that names a domain with 1-2 concrete actions but is not comprehensive.

3 / 5

Completeness

It states both what ("Review a Go change") and when ("when the user asks to inspect a diff for correctness"), but the when clause covers a single trigger rather than the multiple concrete trigger phrases of the level-5 anchor.

4 / 5

Trigger Term Quality

"when the user asks to inspect a diff for correctness" includes natural phrases a user would say ("inspect a diff", "correctness"), with only common synonyms like "code review" or "PR" missing, fitting the good-but-incomplete anchor.

4 / 5

Distinctiveness Conflict Risk

The Go-specific diff-review niche is mostly distinct with minimal conflict risk, though it could overlap with a generic code-review skill, fitting the mostly-distinct anchor rather than the fully-niche level-5 example.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jbaruch/agentic-context-registry
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.